ModelNet-O: A large-scale synthetic dataset for occlusion-aware point cloud classification

Zhongbin Fang, Xia Li, Xiangtai Li, Shen Zhao, Mengyuan Liu

Abstract: Highlights•We introduce a challenging occlusion point cloud classification dataset ModelNet-O.•We propose a robust method, PointMLS, based on a multi-level sampling strategy.•We achieve SoTA results on the ModelNet-O and competitive results on regular datasets.